English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Accurate yield forecasting is essential for making informed policies andlong-term decisions for food security. Earth Observation (EO) data and machinelearning algorithms play a key role in providing a comprehensive and timelyview of crop conditions from field to national scales. However, machinelearning algorithms' prediction accuracy is often harmed by spatialheterogeneity caused by exogenous factors not reflected in remote sensing data,such as differences in crop management strategies. In this paper, we proposeand investigate a simple technique called state-wise additive bias toexplicitly address the cross-region yield heterogeneity in Kazakhstan. Comparedto baseline machine learning models (Random Forest, CatBoost, XGBoost), ourmethod reduces the overall RMSE by 8.9\% and the highest state-wise RMSE by28.37\%. The effectiveness of state-wise additive bias indicates machinelearning's performance can be significantly improved by explicitly addressingthe spatial heterogeneity, motivating future work on spatial-aware machinelearning algorithms for yield forecasts as well as for general geospatialforecasting problems.

Improve State-Level Wheat Yield Forecasts in Kazakhstan on GEOGLAM's EO Data by Leveraging A Simple Spatial-Aware Technique